Automatic recognition of cylinders and planes from unstructured point clouds
Само за регистроване кориснике
2022
Чланак у часопису (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
3D scanning devices are traditionally employed in reverse engineering tasks that can be carried out semi-automatically, with user assistance. However, their application in manufacturing process control requires automatic point cloud segmentation and extraction of geometric primitives. In this paper, we propose a method for automatic recognition of planes and cylinders (most frequently encountered geometric primitives in mechanical engineering) from unstructured point clouds. The method is based on the scatter of data during least squares fitting of second order surfaces. It consists of three phases and the first phase represents automatic point cloud segmentation. The second phase deals with merging of over-segmented regions and surfaces parameters estimation, whereas the final phase provides extraction of recognized geometric primitives. The method is experimentally verified using three real-world case studies, and its performances are compared with two state of the art recognition al...gorithms. The results have shown that the proposed method outperforms alternative approaches in terms of appropriately recognized planes and cylinders without surface type confusion, as well as when the recognition of non-existent primitives is considered. In addition, the method determines surfaces parameters with high accuracy.
Кључне речи:
Reverse engineering / Planes recognition / Cylinders recognition / 3D point cloud processingИзвор:
Visual Computer, 2022, 38, 4329-4352Издавач:
- Springer, New York
Финансирање / пројекти:
- MISSION4.0 - Deep Machine Learning and Swarm Intelligence-Based Optimization Algorithms for Control and Scheduling of Cyber-Physical Systems in Industry 4.0 (RS-6523109)
- Министарство науке, технолошког развоја и иновација Републике Србије, институционално финансирање - 200105 (Универзитет у Београду, Машински факултет) (RS-200105)
- AI-MISSION4.0, 2020-2022
DOI: 10.1007/s00371-021-02299-9
ISSN: 0178-2789
WoS: 000697092400001
Scopus: 2-s2.0-85115170724
Колекције
Институција/група
Mašinski fakultetTY - JOUR AU - Marković, Veljko AU - Jakovljević, Živana AU - Budak, Igor PY - 2022 UR - https://machinery.mas.bg.ac.rs/handle/123456789/91 AB - 3D scanning devices are traditionally employed in reverse engineering tasks that can be carried out semi-automatically, with user assistance. However, their application in manufacturing process control requires automatic point cloud segmentation and extraction of geometric primitives. In this paper, we propose a method for automatic recognition of planes and cylinders (most frequently encountered geometric primitives in mechanical engineering) from unstructured point clouds. The method is based on the scatter of data during least squares fitting of second order surfaces. It consists of three phases and the first phase represents automatic point cloud segmentation. The second phase deals with merging of over-segmented regions and surfaces parameters estimation, whereas the final phase provides extraction of recognized geometric primitives. The method is experimentally verified using three real-world case studies, and its performances are compared with two state of the art recognition algorithms. The results have shown that the proposed method outperforms alternative approaches in terms of appropriately recognized planes and cylinders without surface type confusion, as well as when the recognition of non-existent primitives is considered. In addition, the method determines surfaces parameters with high accuracy. PB - Springer, New York T2 - Visual Computer T1 - Automatic recognition of cylinders and planes from unstructured point clouds EP - 4352 SP - 4329 VL - 38 DO - 10.1007/s00371-021-02299-9 ER -
@article{ author = "Marković, Veljko and Jakovljević, Živana and Budak, Igor", year = "2022", abstract = "3D scanning devices are traditionally employed in reverse engineering tasks that can be carried out semi-automatically, with user assistance. However, their application in manufacturing process control requires automatic point cloud segmentation and extraction of geometric primitives. In this paper, we propose a method for automatic recognition of planes and cylinders (most frequently encountered geometric primitives in mechanical engineering) from unstructured point clouds. The method is based on the scatter of data during least squares fitting of second order surfaces. It consists of three phases and the first phase represents automatic point cloud segmentation. The second phase deals with merging of over-segmented regions and surfaces parameters estimation, whereas the final phase provides extraction of recognized geometric primitives. The method is experimentally verified using three real-world case studies, and its performances are compared with two state of the art recognition algorithms. The results have shown that the proposed method outperforms alternative approaches in terms of appropriately recognized planes and cylinders without surface type confusion, as well as when the recognition of non-existent primitives is considered. In addition, the method determines surfaces parameters with high accuracy.", publisher = "Springer, New York", journal = "Visual Computer", title = "Automatic recognition of cylinders and planes from unstructured point clouds", pages = "4352-4329", volume = "38", doi = "10.1007/s00371-021-02299-9" }
Marković, V., Jakovljević, Ž.,& Budak, I.. (2022). Automatic recognition of cylinders and planes from unstructured point clouds. in Visual Computer Springer, New York., 38, 4329-4352. https://doi.org/10.1007/s00371-021-02299-9
Marković V, Jakovljević Ž, Budak I. Automatic recognition of cylinders and planes from unstructured point clouds. in Visual Computer. 2022;38:4329-4352. doi:10.1007/s00371-021-02299-9 .
Marković, Veljko, Jakovljević, Živana, Budak, Igor, "Automatic recognition of cylinders and planes from unstructured point clouds" in Visual Computer, 38 (2022):4329-4352, https://doi.org/10.1007/s00371-021-02299-9 . .